# US 2021/0279867 A1 · Crop yield estimation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279867 A1 - Document ID: US20210279867A1 - Status: Published application - Kind: A1 - Application number: 17/196,674 - Filed: 2021-03-09 - Published: 2021-09-09 - Earliest claimed: 2020-03-09 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Bruno Silva; RENATO LUIZ DE FREITAS CUNHA; ANA PAULA APPEL; Eduardo Rocha Rodrigues - Web page: https://patentgrep.com/patent/US20210279867A1 ## CPC - G06T 7/11: Region-based segmentation - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06T 7/0012: {Biomedical image inspection} - G06V 20/17: taken from planes or by drones - G06V 20/188: {Vegetation} - G06T 2207/10032: Satellite or aerial image; Remote sensing - G06T 2207/20081: Training; Learning - G06T 2207/30004: Biomedical image processing - G06T 2207/30188: Vegetation; Agriculture - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The present disclosure provides for crop yield estimation by identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data. ## Claims ### Claim 1 A method comprising: identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data. ### Claim 2 (depends on 1) The method of claim 1, further comprising: identifying a path for a data collector to reach the plurality of data collection points according to a lowest cost according to a cost-function associated with a movement type of the data collector between each data collection point of the plurality of data collection points. ### Claim 3 (depends on 1) The method of claim 1, wherein the plurality of regions describe zones of the field in which the yield of the crop are predicted to be clustered based on the growth metrics, which include one or more of: vegetation indexes visible in images of the field; soil conditions throughout the field; fertilizer application levels throughout the field; and pest control application levels throughout the field. ### Claim 4 (depends on 3) The method of claim 3, further comprising: refining the model used to identify the plurality of regions to identify a plurality of new regions within the field, wherein the new regions are identified based on a clustering of the in-field data collected from the plurality of regions. ### Claim 5 (depends on 3) The method of claim 3, further comprising: outputting an intermediate crop development metric via an intermediate model according to a plurality of parameters and the in-field data, wherein the intermediate crop development metric indicates a progress of the crop; refining the plurality of parameters of the intermediate model according to the in-field data; and wherein the intermediate crop development metric is related to one or more of: a leaf area index; a development stage; a dry weight; and a number of seeds per plant. ### Claim 6 (depends on 1) The method of claim 1, further comprising: identifying a second field in which the crop is grown; identifying a second plurality of regions within the second field; identifying a second plurality of data collection points in the second plurality of regions; receiving second in-field data linked to the data collection points of the second plurality; and predicting a second yield for the crop in the second field based on the second in-field data and the yield predicted for the field. ### Claim 7 (depends on 6) The method of claim 6, wherein a first given region of the plurality of regions is linked to a second given region of the second plurality of regions as a single region that spans the field and the second field. ### Claim 8 A system comprising: a processor; and a memory storage device including processor executable instructions to perform an operation comprising: identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data. ### Claim 9 (depends on 8) The system of claim 8, the operation further comprising: identifying a path for a data collector to reach the plurality of data collection points according to a lowest cost according to a cost-function associated with a movement type of the data collector between each data collection point of the plurality of data collection points. ### Claim 10 (depends on 8) The system of claim 8, wherein the plurality of regions describe zones of the field in which the yield of the crop are predicted to be clustered based on one or more of: vegetation indexes visible in images of the field; soil conditions throughout the field; fertilizer application levels throughout the field; and pest control application levels throughout the field. ### Claim 11 (depends on 10) The system of claim 10, the operation further comprising: refining the model used to identify the plurality of regions to identify a plurality of new regions within the field, wherein the new regions are identified based on a clustering of the in-field data collected from the plurality of regions. ### Claim 12 (depends on 10) The system of claim 10, the operation further comprising: outputting an intermediate crop development metric via an intermediate model according to a plurality of parameters and the in-field data, wherein the intermediate crop development metric indicates a progress of the crop; refining the plurality of parameters of the intermediate model according to the in-field data; and wherein the intermediate crop development metric is related to one or more of: a leaf area index; a development stage; a dry weight; and a number of seeds per plant ### Claim 13 (depends on 8) The system of claim 8, the operation further comprising: identifying a second field in which the crop is grown; identifying a second plurality of regions within the second field; identifying a second plurality of data collection points in the second plurality of regions; receiving second in-field data linked to the data collection points of the second plurality; and predicting a second yield for the crop in the second field based on the second in-field data and the yield predicted for the field. ### Claim 14 (depends on 13) The system of claim 13, wherein a first given region of the plurality of regions is linked to a second given region of the second plurality of regions as a single region that spans the field and the second field. ### Claim 15 A computer readable storage device including instructions that when performed by a processor, enable the processor to: identify, via image processing, a field in which a crop is grown; identify a plurality of regions within the field; identify, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receive in-field data linked to the data collection points of the plurality; and predict a yield for the crop in the field based on the in-field data. ### Claim 16 (depends on 15) The computer readable storage device of claim 15, wherein the instructions, when performed, further enable the processor to: identify a path for a data collector to reach the plurality of data collection points according to a lowest cost according to a cost-function associated with a movement type of the data collector between each data collection point of the plurality of data collection points. ### Claim 17 (depends on 15) The computer readable storage device of claim 15, wherein the plurality of regions describe zones of the field in which the yield of the crop are predicted to be clustered based on one or more of: vegetation indexes visible in images of the field; soil conditions throughout the field; fertilizer application levels throughout the field; and pest control application levels throughout the field. ### Claim 18 (depends on 17) The computer readable storage device of claim 17, wherein the instructions, when performed, further enable the processor to: refine the model used to identify the plurality of regions to identify a plurality of new regions within the field, wherein the new regions are identified based on a clustering of the in-field data collected from the plurality of regions. ### Claim 19 (depends on 17) The computer readable storage device of claim 17, wherein the instructions, when performed, further enable the processor to: output an intermediate crop development metric via an intermediate model according to a plurality of parameters and the in-field data, wherein the intermediate crop development metric indicates a progress of the crop; refine the plurality of parameters of the intermediate model according to the in-field data; and wherein the intermediate crop development metric is related to one or more of: a leaf area index; a development stage; a dry weight; and a number of seeds per plant. ### Claim 20 (depends on 15) The computer readable storage device of claim 15, wherein the instructions, when performed, further enable the processor to: identify a second field in which the crop is grown; identify a second plurality of regions within the second field; identify a second plurality of data collection points in the second plurality of regions; receive second in-field data linked to the data collection points of the second plurality; and predict a second yield for the crop in the second field based on the second in-field data and the yield predicted for the field.